Treatment of depression using machine learning

Abstract

Provided herein are, inter alia, methods for identifying subjects suffering from depression that will respond to treatment with an antidepressant.

What is claimed is: 
     
         1 . A method of predicting a response of a patient having depression to a placebo or sham treatment comprising:
 obtaining first data comprising brain signals of the patient from an electroencephalogram (EEG);   applying a machine learning model to a representation of the first data to obtain a placebo response metric for the patient,   the machine learning model configured to:
 generate, based at least on a first training data corresponding to one or more brain signals obtained by EEG of a first plurality of subjects having depression and a placebo outcome metric associated with each of the first plurality of subjects after administration of a placebo or treatment with a sham treatment, a first plurality of latent signals, and 
 generate, based at least on a feature of each of the first plurality of latent signals and first data, the placebo response metric for the patient, wherein the feature is a band power, a power-envelope connectivity, a weighted phase-lag index, an imaginary coherence, a cordance, an approximate entropy, a Shannon entropy, a cross-frequency coupling, or any combination of any of the foregoing. 
   
     
     
         2 . The method of  claim 1 , wherein the brain signals for the patient and subjects are in a alpha frequency range. 
     
     
         3 . The method of  claim 1 , wherein the brain signals for the patient and subjects are in a beta frequency range. 
     
     
         4 . The method of  claim 1 , wherein the brain signals for the patient and subjects are in a theta frequency range. 
     
     
         5 . The method of  claim 1 , wherein the first data further comprises at least one of transcranial magnetic stimulation electroencephalogram (TMS-EEG) data, a magnetoencephalography (MEG) data, a functional magnetic resonance imaging (fMRI) data, and a functional near-infrared spectroscopy (fNIRS) data. 
     
     
         6 . The method of  claim 1 , wherein the feature is an imaginary coherence. 
     
     
         7 . The method of  claim 1 , wherein the feature is a power-envelope connectivity. 
     
     
         8 . The method of  claim 1 , wherein the feature is a band power. 
     
     
         9 . A non-transitory computer readable medium comprising computer readable code for predicting a response of a patient having depression to a placebo or sham treatment, the computer readable code executable by one or more processors to:
 obtain first data comprising brain signals of the patient from an electroencephalogram (EEG);   apply a machine learning model to a representation of the first data to obtain a placebo response metric for the patient,   the machine learning model configured to:
 generate, based at least on a first training data corresponding to one or more brain signals obtained by EEG of a first plurality of subjects having depression and a placebo outcome metric associated with each of the first plurality of subjects after administration of a placebo or treatment with a sham treatment, a first plurality of latent signals, and 
 generate, based at least on a feature of each of the first plurality of latent signals and first data, the placebo response metric for the patient, wherein the feature is a band power, a power-envelope connectivity, a weighted phase-lag index, an imaginary coherence, a cordance, an approximate entropy, a Shannon entropy, a cross-frequency coupling, or any combination of any of the foregoing. 
   
     
     
         10 . The non-transitory computer readable medium of  claim 9 , wherein the brain signals for the patient and subjects are in a alpha frequency range. 
     
     
         11 . The non-transitory computer readable medium of  claim 9 , wherein the brain signals for the patient and subjects are in a beta frequency range. 
     
     
         12 . The non-transitory computer readable medium of  claim 9 , wherein the brain signals for the patient and subjects are in a theta frequency range. 
     
     
         13 . The non-transitory computer readable medium of  claim 9 , wherein the first data further comprises at least one of transcranial magnetic stimulation electroencephalogram (TMS-EEG) data, a magnetoencephalography (MEG) data, a functional magnetic resonance imaging (fMRI) data, and a functional near-infrared spectroscopy (fNIRS) data. 
     
     
         14 . The non-transitory computer readable medium of  claim 9 , wherein the feature is an imaginary coherence. 
     
     
         15 . The non-transitory computer readable medium of  claim 9 , wherein the feature is a power-envelope connectivity. 
     
     
         16 . The non-transitory computer readable medium of  claim 9 , wherein the feature is a band power. 
     
     
         17 . A system comprising:
 one or more processors; and   one or more computer readable media comprising computer readable code executable by the one or more processors to:   obtain first data comprising brain signals of a patient from an electroencephalogram (EEG);   apply a machine learning model to a representation of the first data to obtain a placebo response metric for the patient,   the machine learning model configured to:
 generate, based at least on a first training data corresponding to one or more brain signals obtained by EEG of a first plurality of subjects having depression and a placebo outcome metric associated with each of the first plurality of subjects after administration of a placebo or treatment with a sham treatment, a first plurality of latent signals, and 
 generate, based at least on a feature of each of the first plurality of latent signals and first data, the placebo response metric for the patient, wherein the feature is a band power, a power-envelope connectivity, a weighted phase-lag index, an imaginary coherence, a cordance, an approximate entropy, a Shannon entropy, a cross-frequency coupling, or any combination of any of the foregoing. 
   
     
     
         18 . The system of  claim 17 , wherein the brain signals for the patient and subjects are in a alpha frequency range. 
     
     
         19 . The system of  claim 17 , wherein the brain signals for the patient and subjects are in a beta frequency range. 
     
     
         20 . The system of  claim 17 , wherein the brain signals for the patient and subjects are in a theta frequency range.